Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    anych
    -0.07
     crack
    -0.07
    éĶĭ
    -0.06
    ãģ£ãģ¦ãģįãģŁ
    -0.06
    enek
    -0.06
    cken
    -0.06
    ả
    -0.06
    ision
    -0.06
    arrant
    -0.06
    åīĩ
    -0.06
    POSITIVE LOGITS
    deo
    0.06
    oÃłi
    0.06
    atto
    0.06
    adir
    0.06
    496
    0.06
    erval
    0.06
    ombre
    0.06
     âĹĦ
    0.06
    anj
    0.06
    note
    0.06
    Act Density 0.024%

    No Known Activations